finalproject

Loading and tidying the Yelp business dataset

business <- read_csv("./data/business.csv") %>% 
  mutate(name = str_sub(name, 2, -2)) %>% 
  mutate(address = str_sub(address, 2, -2)) %>% 
  filter(neighborhood != "Downtown Tampa" & neighborhood != "North Valley")

## Parsed with column specification:
## cols(
##   business_id = col_character(),
##   name = col_character(),
##   neighborhood = col_character(),
##   address = col_character(),
##   city = col_character(),
##   state = col_character(),
##   postal_code = col_integer(),
##   latitude = col_double(),
##   longitude = col_double(),
##   stars = col_double(),
##   review_count = col_integer(),
##   is_open = col_integer(),
##   categories = col_character()
## )

categories <- business %>% 
  select(business_id, categories) %>% 
  separate(categories, into = c("cat1", "cat2", "cat3", "cat4", "cat5", "cat6", "cat7", "cat8", "cat9", "cat10", "cat11", "cat12", "cat13", "cat14", "cat15", "cat16", "cat17", "cat18", "cat19", "cat20", "cat21", "cat22", "cat23", "cat24", "cat25"), sep  = ";") %>% 
  gather(key = "cat_id", value = "category", starts_with("cat")) %>% 
  select(-cat_id)

## Warning: Expected 25 pieces. Additional pieces discarded in 1 rows [5602].

## Warning: Expected 25 pieces. Missing pieces filled with `NA` in 21884
## rows [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19,
## 20, ...].

restaurant_ids <- categories %>% 
  filter(category == "Restaurants") %>% 
  distinct(business_id)

restaurants <- business %>% 
  left_join(restaurant_ids, by = "business_id") %>% 
  select(-categories)

rm(business)

Loading and tidying the attributes dataset

attributes <- read_csv("./data/attributes.csv") %>% 
  janitor::clean_names() %>% 
  select(business_id, alcohol)

## Parsed with column specification:
## cols(
##   .default = col_character()
## )

## See spec(...) for full column specifications.

Joining the business and attributes datasets

restaurants <- restaurants %>% 
  left_join(attributes, by = "business_id")

Creating a plotly of restaurant locations

Center of Las Vegas: 36.1699° N, 115.1398° W. Plotly displayed is surrounds this center by 0.5 degrees longitude and latitude.

restaurants %>% 
  filter(latitude > 35.6699 & latitude < 36.6699) %>% 
  filter(longitude < -114.6398 & longitude > -115.6398) %>%
  plot_ly(x = ~longitude, y = ~latitude, type = "scatter", mode = "markers",
          alpha = 0.5, 
          color = ~stars, hoverinfo = 'text',
        text = ~paste(name, " @", neighborhood, "\n", address, "\n", city, ", ", state, postal_code, "\n", stars, "stars on Yelp")) %>%
  layout(xaxis = list(title = "Longitude"),
         yaxis = list(title = "Latitude"))

<<<<<<< HEAD ======= >>>>>>> b3016a79d0174192eca54e532ba8f779bfb4cbc4

exploratory stuff

restaurants %>% 
  group_by(neighborhood) %>% 
<<<<<<< HEAD
  count()

## # A tibble: 16 x 2
## # Groups:   neighborhood [16]
##    neighborhood        n
##    <chr>           <int>
##  1 Anthem             75
##  2 Centennial        815
##  3 Chinatown         834
##  4 Downtown         1837
##  5 Eastside         1886
##  6 Northwest        1044
##  7 South Summerlin   351
##  8 Southeast        2999
##  9 Southwest        1083
## 10 Spring Valley    2710
## 11 Summerlin         896
## 12 Sunrise           704
## 13 The Lakes         162
## 14 The Strip        2734
## 15 University        261
## 16 Westside         3494

======= count() %>% knitr::kable()

neighborhood	n
Anthem	75
Centennial	815
Chinatown	834
Downtown	1837
Eastside	1886
Northwest	1044
South Summerlin	351
Southeast	2999
Southwest	1083
Spring Valley	2710
Summerlin	896
Sunrise	704
The Lakes	162
The Strip	2734
University	261
Westside	3494

>>>>>>> b3016a79d0174192eca54e532ba8f779bfb4cbc4

restaurants %>%
  filter(alcohol == "True" | is_open == "True") %>% 
  group_by(neighborhood) %>% 
  count() %>% 
  knitr::kable()

neighborhood	n
Anthem	3
Centennial	46
Chinatown	23
Downtown	99
Eastside	66
Northwest	41
South Summerlin	45
Southeast	171
Southwest	41
Spring Valley	85
Summerlin	39
Sunrise	30
The Lakes	4
The Strip	67
University	12
Westside	162

<<<<<<< HEAD

  restaurants %>%
=======
restaurants %>%
>>>>>>> b3016a79d0174192eca54e532ba8f779bfb4cbc4
  filter(alcohol == "False" | is_open == "True") %>% 
  group_by(neighborhood) %>% 
  count() %>% 
  knitr::kable()



neighborhood
n




Anthem
2


Centennial
14


Chinatown
16


Downtown
44


Eastside
32


Northwest
15


South Summerlin
9


Southeast
87


Southwest
21


Spring Valley
35


Summerlin
11


Sunrise
15


The Lakes
3


The Strip
168


University
2


Westside
74



restaurants %>% 
select(business_id, neighborhood, stars) %>% 
  distinct() %>% 
  group_by(neighborhood, stars) %>% 
  tally %>% 
  rename(my_count = n) %>% 
  spread(key = stars, value = my_count) %>% 
  knitr::kable()



neighborhood
1
1.5
2
2.5
3
3.5
4
4.5
5




Anthem
NA
1
8
4
9
10
10
16
17


Centennial
14
18
47
77
113
138
142
101
165


Chinatown
24
11
40
60
94
168
184
141
112


Downtown
44
53
91
126
214
284
351
309
365


Eastside
64
64
139
198
268
315
367
229
242


Northwest
21
17
61
90
113
183
195
132
232


South Summerlin
1
2
10
22
44
84
75
54
59


Southeast
78
83
165
256
377
474
543
431
592


Southwest
13
22
49
89
114
166
204
185
241


Spring Valley
41
46
110
193
270
392
460
478
720


Summerlin
17
11
43
62
106
128
157
127
245


Sunrise
28
33
64
90
89
112
109
86
93


The Lakes
1
3
9
10
12
20
36
23
48


The Strip
19
37
117
277
448
596
629
383
228


University
5
10
15
24
30
57
48
45
27


Westside
60
81
156
278
369
542
624
550
834



restaurants %>%
  mutate(review_count = as.numeric(review_count)) %>% 
  select(business_id, neighborhood, review_count) %>% 
  group_by(neighborhood) %>% 
  summarise(Average_Number_of_Reviews = mean(review_count)) %>% 
  knitr::kable()



neighborhood
Average_Number_of_Reviews




Anthem
42.76000


Centennial
42.26012


Chinatown
91.99400


Downtown
55.80512


Eastside
55.82927


Northwest
31.30843


South Summerlin
72.31909


Southeast
46.21407


Southwest
57.39797


Spring Valley
47.95314


Summerlin
34.29018


Sunrise
16.83097


The Lakes
35.55556


The Strip
182.80102


University
56.02682


Westside
40.56898



<<<<<<< HEAD
=======

neighborhood	n
Anthem	2
Centennial	14
Chinatown	16
Downtown	44
Eastside	32
Northwest	15
South Summerlin	9
Southeast	87
Southwest	21
Spring Valley	35
Summerlin	11
Sunrise	15
The Lakes	3
The Strip	168
University	2
Westside	74

neighborhood	1	1.5	2	2.5	3	3.5	4	4.5	5
Anthem	NA	1	8	4	9	10	10	16	17
Centennial	14	18	47	77	113	138	142	101	165
Chinatown	24	11	40	60	94	168	184	141	112
Downtown	44	53	91	126	214	284	351	309	365
Eastside	64	64	139	198	268	315	367	229	242
Northwest	21	17	61	90	113	183	195	132	232
South Summerlin	1	2	10	22	44	84	75	54	59
Southeast	78	83	165	256	377	474	543	431	592
Southwest	13	22	49	89	114	166	204	185	241
Spring Valley	41	46	110	193	270	392	460	478	720
Summerlin	17	11	43	62	106	128	157	127	245
Sunrise	28	33	64	90	89	112	109	86	93
The Lakes	1	3	9	10	12	20	36	23	48
The Strip	19	37	117	277	448	596	629	383	228
University	5	10	15	24	30	57	48	45	27
Westside	60	81	156	278	369	542	624	550	834

neighborhood	Average_Number_of_Reviews
Anthem	42.76000
Centennial	42.26012
Chinatown	91.99400
Downtown	55.80512
Eastside	55.82927
Northwest	31.30843
South Summerlin	72.31909
Southeast	46.21407
Southwest	57.39797
Spring Valley	47.95314
Summerlin	34.29018
Sunrise	16.83097
The Lakes	35.55556
The Strip	182.80102
University	56.02682
Westside	40.56898


>>>>>>> b3016a79d0174192eca54e532ba8f779bfb4cbc4



Creating a plotly of open and closed restaurant compared to their rating on Yelp
restaurants %>% 
  mutate(stars = if_else(stars == 1, "1",
                         if_else(stars == 1.5, "1.5",
                                 if_else(stars == 2, "2",
                                         if_else(stars == 2.5, "2.5",
                                                 if_else(stars == 3, "3",
                                                         if_else(stars == 4, "4",
                                                                 if_else(stars == 4.5, "4.5", "5"))))))),
         review_count = as.numeric(review_count)) %>% 
  group_by(stars) %>% 
  plot_ly(x = ~stars, y = ~review_count, color = ~stars, type = "bar", colors = "Set3") %>% 
  layout(xaxis = list(title = "Stars"),
         yaxis = list(title = "Number of Reviews"))



Plots of Restaurants
popular <- categories %>% 
  filter(category == "Restaurants" | category == "Food") %>% 
  distinct(business_id) %>% 
  left_join(categories, by = "business_id") %>% 
  filter(category %in% c("Bars", "Breakfast & Brunch", "Chinese", "Italian", "Mexican", "Chicken Wings", "Salad", "Sushi Bars", "Pizza", "Steakhouses"))

restaurants %>% 
  select(business_id, neighborhood) %>% 
  inner_join(popular) %>% 
  distinct() %>% 
  group_by(neighborhood, category) %>% 
  tally() %>% 
  plotly::plot_ly(x = ~neighborhood, y = ~n, type = 'bar', color = ~category, hoverinfo = 'text',
        text = ~paste(neighborhood, " has ",
                      n, " ", category, " restaurants.")) %>%
  layout(yaxis = list(title = "Restaurants"), xaxis = list(title = "", tickangle = -45), barmode = 'stack')
## Joining, by = "business_id"
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors

## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors



<<<<<<< HEAD

i guess another plot? we shall see

Plots of Restaurants
popular <- categories %>% 
  filter(category == "Restaurants" | category == "Food") %>% 
  distinct(business_id) %>% 
  left_join(categories, by = "business_id") %>% 
  filter(category %in% c("Bars", "Breakfast & Brunch", "Chinese", "Italian", "Mexican", "Chicken Wings", "Salad", "Sushi Bars", "Pizza", "Steakhouses"))

restaurants %>% 
  select(business_id, neighborhood) %>% 
  inner_join(popular) %>% 
  distinct() %>% 
  group_by(neighborhood, category) %>% 
  tally() %>% 
  plotly::plot_ly(x = ~neighborhood, y = ~n, type = 'bar', color = ~category, hoverinfo = 'text',
        text = ~paste(neighborhood, " has ",
                      n, " ", category, " restaurants.")) %>%
  layout(yaxis = list(title = "Restaurants"), xaxis = list(title = "", tickangle = -45), barmode = 'stack')
## Joining, by = "business_id"
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors

## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors





Geographic Plot by Categories
restaurants %>% 
  inner_join(popular) %>% 
  plot_ly(x = ~longitude, y = ~latitude, type = "scatter", mode = "markers",
          alpha = 0.9, 
          color = ~category, hoverinfo = 'text',
        text = ~paste(name, " @", neighborhood, "\n", address, "\n", city, ", ", state, postal_code, "\n", stars, "star", category, "on Yelp.")) %>%
  layout(xaxis = list(title = "Longitude"),
         yaxis = list(title = "Latitude"))
## Joining, by = "business_id"
## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors

## Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
## Returning the palette you asked for with that many colors


=======
>>>>>>> b3016a79d0174192eca54e532ba8f779bfb4cbc4